A scaled conjugate gradient algorithm for fast supervised learning

Backpropagation Learning for Multi-layer Feed-forward Neural Networks Using the Conjugate Gradient Method. Ieee Transactions on Neural Networks, 1991. [31] M. F. Mller. a Scaled Conjugate Gradient Algorithm for Fast Supervised Learning. Technical Report Pb-339

Comparison of Neural Network Training Functions for Hematoma Classification in Brain CT Images

Classification is one of the most important task in application areas of artificial neural networks (ANN).Training neural networks is a complex task in the supervised learning field of research. The main difficulty in adopting ANN is to find the most appropriate combination of learning, transfer and training function for the classification task. We compared the performances of three types of tr...

Link Propagation: A Fast Semi-supervised Learning Algorithm for Link Prediction

We propose Link Propagation as a new semi-supervised learning method for link prediction problems, where the task is to predict unknown parts of the network structure by using auxiliary information such as node similarities. Since the proposed method can fill in missing parts of tensors, it is applicable to multi-relational domains, allowing us to handle multiple types of links simultaneously. ...

An E cient PCA-type Learning Based on Scaled Conjugate Gradient Algorithm for Fast Signal Subspace Decomposition

Nonlinear PCA type learning has been recently suggested for signal subspace decomposition and sinusoidal frequencies tracking, which outperformed the linear PCA based methods and traditional least squares algorithms. Currently, nonlinear PCA algorithms are directly generalized from linear ones that based on gradient descent (GD) technique. The convergence behavior of gradient descent is depende...

A Classical Algorithm for Avoiding Local Minima

Conventional methods of supervised learning are inevitably faced with the problem of local minima; evidence is presented that conjugate gradient and quasi-Newton techniques are particularly susceptible to being trapped in sub-optimal solutions. A new classical technique is presented which by the use of a homotopy on the range of the target outputs allows supervised learning methods to find a gl...